# Collaborative Rational Speech Act: Pragmatic Reasoning for Multi-Turn Dialog

arXiv: https://arxiv.org/abs/2507.14063 · HTML: https://mlsanity.com/paper/2507.14063/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 43 references that are in the map.
- First posted on arXiv 18 Jul 2025.

## Builds on (most cited first, 20 of 20)

- [Deep Reinforcement Learning for Dialogue Generation](https://mlsanity.com/paper/1606.01541/) (2016)
- [A Network-based End-to-End Trainable Task-oriented Dialogue System](https://mlsanity.com/paper/1604.04562/) (2016)
- [Open Problems in Cooperative AI](https://mlsanity.com/paper/2012.08630/) (2020)
- [Reward-rational (implicit) choice: A unifying formalism for reward learning](https://mlsanity.com/paper/2002.04833/) (2020)
- [Learning Symmetric Collaborative Dialogue Agents with Dynamic Knowledge Graph Embeddings](https://mlsanity.com/paper/1704.07130/) (2017)
- [Inferring Rewards from Language in Context](https://mlsanity.com/paper/2204.02515/) (2022)
- [Perspective-taking and Pragmatics for Generating Empathetic Responses Focused on Emotion Causes](https://mlsanity.com/paper/2109.08828/) (2021)
- [Pragmatically Informative Image Captioning with Character-Level Inference](https://mlsanity.com/paper/1804.05417/) (2018)
- [Pragmatically Informative Text Generation](https://mlsanity.com/paper/1904.01301/) (2019)
- [When redundancy is useful: A Bayesian approach to 'overinformative' referring expressions](https://mlsanity.com/paper/1903.08237/) (2019)
- [A Rate-Distortion view of human pragmatic reasoning](https://mlsanity.com/paper/2005.06641/) (2020)
- [Planning, Inference and Pragmatics in Sequential Language Games](https://mlsanity.com/paper/1805.11774/) (2018)
- [Lost in Machine Translation: A Method to Reduce Meaning Loss](https://mlsanity.com/paper/1902.09514/) (2019)
- [RSA-Control: A Pragmatics-Grounded Lightweight Controllable Text Generation Framework](https://mlsanity.com/paper/2410.19109/) (2024)
- [AI Agentic workflows and Enterprise APIs: Adapting API architectures for the age of AI agents](https://mlsanity.com/paper/2502.17443/) (2025)
- [MDDial: A Multi-turn Differential Diagnosis Dialogue Dataset with Reliability Evaluation](https://mlsanity.com/paper/2308.08147/) (2023)
- [GLIMPSE: Pragmatically Informative Multi-Document Summarization for Scholarly Reviews](https://mlsanity.com/paper/2406.07359/) (2024)
- [Collaborative Information Bottleneck](https://mlsanity.com/paper/1604.01433/) (2016)
- [Towards End-to-End Learning for Efficient Dialogue Agent by Modeling Looking-ahead Ability](https://mlsanity.com/paper/1908.05408/) (2019)
- [Towards a Fully Interpretable and More Scalable RSA Model for Metaphor Understanding](https://mlsanity.com/paper/2404.02983/) (2024)

## Built on by (most cited first, 2 of 2)

- [LLMs Infer Cultural Context but Fail to Apply It When Responding](https://mlsanity.com/paper/2606.17688/) (2026)
- [Flout at Your Own Risk: LLMs Struggle with Pragmatic Cooperativity Under Epistemic Asymmetry](https://mlsanity.com/paper/2607.11053/) (2026)

## Abstract (arXiv)

As AI systems take on collaborative roles, they must reason about shared goals and beliefs-not just generate fluent language. The Rational Speech Act (RSA) framework offers a principled approach to pragmatic reasoning, but existing extensions face challenges in scaling to multi-turn, collaborative scenarios. In this paper, we introduce Collaborative Rational Speech Act (CRSA), an information-theoretic (IT) extension of RSA that models multi-turn dialog by optimizing a gain function adapted from rate-distortion theory. This gain is an extension of the gain model that is maximized in the original RSA model but takes into account the scenario in which both agents in a conversation have private information and produce utterances conditioned on the dialog. We demonstrate the effectiveness of CRSA on referential games and template-based doctor-patient dialogs in the medical domain. Empirical results show that CRSA yields more consistent, interpretable, and collaborative behavior than existing baselines-paving the way for more pragmatic and socially aware language agents.